Inference Intern
San Jose • Intern
Posted 10mo ago
Job Location
San Jose
Tech Stack
Remote Work Policy
On-site
Employment Type
Intern
Categories
AI Infrastructure Engineer
About the job
Etched is building hardware for frontier intelligence, focusing on inference. We are seeking talented interns to contribute to the design of next-generation AI accelerators. This role involves developing and optimizing compute architectures for exceptional performance and efficiency in inference workloads, tackling cutting-edge architectural problems and performance modeling.
Responsibilities
- Support porting state-of-the-art models to our architecture, building programming abstractions and testing capabilities for rapid iteration.
- Assist in building, enhancing, and scaling our runtime, including multi-node inference, intra-node execution, state management, and error handling.
- Contribute to optimizing routing and communication layers using our collectives.
- Utilize performance profiling and debugging tools to identify bottlenecks and correctness issues.
- Develop a deep understanding of our architecture to co-design HW instructions and model architecture operations for maximum performance.
- Implement high-performance software components for the Model Toolkit.
Requirements
- Progress towards a Bachelor’s, Master’s, or PhD degree in computer science, computer engineering, applied mathematics, or a related field.
- Proficiency in Python and C++.
- Understanding of performance-sensitive or complex distributed software systems (e.g., Linux internals, accelerator architectures, compilers, high-speed interconnects).
- Experience porting applications to non-standard accelerator hardware or platforms.
- Deep knowledge of transformer model architectures and/or inference serving stacks (vLLM, SGLang, etc.).
Benefits
- 12-week paid internship
- Generous housing support for those relocating
- Daily lunch and dinner in our office